Improved Point-Voxel Region Convolutional Neural Network: 3D Object Detectors for Autonomous Driving
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS(2022)
摘要
Recently, 3D object detection based on deep learning has achieved impressive performance in complex indoor and outdoor scenes. Among the methods, the two-stage detection method performs the best; however, this method still needs improved accuracy and efficiency, especially for small size objects or autonomous driving scenes. In this paper, we propose an improved 3D object detection method based on a two-stage detector called the Improved Point-Voxel Region Convolutional Neural Network (IPV-RCNN). Our proposed method contains online training for data augmentation, upsampling convolution and k-means clustering for the bounding box to achieve 3D detection tasks from raw point clouds. The evaluation results on the KITTI 3D dataset show that the IPV-RCNN achieved a 96% mAP, which is 3% more accurate than the state-of-the-art detectors.
更多查看译文
关键词
3D object detection, region proposal method, point cloud data processing
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要